Some Plots Exploring A Jenkins Thread Dump

# knitr::opts_chunk$set(echo = TRUE)
# knitr::opts_chunk$set(fig.width=10) 
library(plyr, warn.conflicts = FALSE)
library(ggplot2, warn.conflicts = FALSE)
library(stringr, warn.conflicts = FALSE)
library(plotly, warn.conflicts = FALSE)
setwd("~/workspace/repos/thread-lock-analysis/R Overview/")

data = read.csv(header = FALSE, "thread_data.csv", col.names = c("ID", "Name", "Prio", "State", "Time"))
data$NewState = sapply(data$State, function(x) {
  if(str_count(x, "wait") > 0) {
    "Waiting"
  }else "Running"
})
data$ID = as.character(data$ID)
data$Name = sapply(data$Name, function(x) {
  name = str_split(x, " from", simplify = TRUE)[1]
  name
  # print(str_sub(name, 1, 20), str_sub(name, 21, length(name)))
  # paste(str_sub(name, 1, 20), str_sub(name, 21, length(name)), sep = "\n")
})

plot = function(data) {
  g <- data %>% ggplot(aes(Date, freq)) + 
    geom_line(aes(color=NewState)) +
    labs(colour="State") +
    ylab("No. Of Threads") +
    xlab("Date/Time") +
    ggtitle("Frequency of Running vs. Waiting Threads Over Time")
  ggplotly(g, tooltip = "all")
}
freq_data = count(data, vars=c("NewState", "Time"))
freq_data$Date = as.POSIXct(freq_data$Time, origin="1970-01-01")
plot(freq_data)

ids = data$ID %>% unique
for(id in ids) {
  len = data[data$ID == id,]$NewState %>% unique %>% length
  if(len > 1) print(id)
}

[1] "139938960125952"
[1] "139938960011264"
[1] "139939373475840"
[1] "139939295565824"
[1] "139940259768320"
[1] "139940256282624"
[1] "139940246902784"
[1] "139939698210816"
[1] "139939632334848"
[1] "139940248473600"

dd = data[data$ID == '139939698210816',]
dd$NewState = as.factor(dd$NewState)
dd$group = 1
my_data = dd
my_data$Time = as.POSIXct(my_data$Time, origin="1970-01-01")
my_data %>% ggplot(aes(Time, NewState, group = group)) + 
  geom_point(aes(color=my_data$Name)) + 
  scale_y_discrete(limits = rev(levels(my_data$NewState))) +
  # theme(legend.position = "top") +
  labs(colour="Thread Name") +
  theme_bw() +
  theme(legend.text=element_text(size=7), legend.position = "top") +
  ylab("State") +
  xlab("Time") +
  ggtitle(paste("Thread ID ", my_data$ID)) +
  guides(colour = guide_legend(nrow = 2, title.position = "top"))

NA
NA

my_data = data[data$ID == '139938960125952',]
my_data$NewState = as.factor(my_data$NewState)
my_data$group = 1
my_data %>% ggplot(aes(Time, NewState, group = group)) + 
  geom_line(aes(color=my_data$Name)) + 
  scale_y_discrete(limits = rev(levels(my_data$NewState))) +
  labs(colour="Thread Name") +
  theme_bw() +
  theme(legend.text=element_text(size=7)) +
  ylab("State") +
  xlab("Time") +
  ggtitle(paste("Thread ID ", my_data$ID))

g <- my_data %>% ggplot(aes(Time, NewState, group = group)) + 
  geom_point(aes(color=my_data$Name)) + 
  scale_y_discrete(limits = rev(levels(my_data$NewState))) +
  labs(colour="Thread Name") +
  theme_bw() +
  theme(legend.text=element_text(size=6), legend.title = element_text(size=7), legend.position = "top", legend.title.align = 0) +
  ylab("State") +
  xlab("Time") +
  ggtitle(paste("Thread ID ", my_data$ID))
g

freq_data = count(data, vars=c("Prio", "Time"))
freq_data$Date = as.POSIXct(freq_data$Time, origin="1970-01-01")
freq_data$Prio = freq_data$Prio %>% sapply(function(x){if(x == -1){"Missing"}else{x}})
freq_data$Prio = as.factor(freq_data$Prio)
g <- freq_data %>% ggplot(aes(Date, freq)) + 
    geom_line(aes(color=Prio)) +
    labs(colour="Priority") +
    ylab("No. Of Threads") +
    xlab("Date/Time") +
    ggtitle("Frequency of Threads With Diff. Priorities Over Time") 
ggplotly(g, tooltip = "all")